Pasar al contenido principal

DESARROLLO DE MODELOS 3D DE MICROTEXTURA DEL ESMALTE Y EXPOSICION DE LA DENTINA EN PRIMATES PARA INFERIR ADAPTACIONES ECOLOGICAS Y DIETA EN HOMININOS DEL PLIO-PLEISTOCENO

PID2023-148818NB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE BARCELONA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Dietary ecology and niche differentiation of Pliocene-Pleistocene papionins from the Turkana Basin inferred from buccal dental microwear texture analysis and machine-learning approaches

  • Hidalgo-Trujillo, Luis
  • Estebaranz-Sánchez, Ferran
  • Dyowe-Roig, Albert E
  • Bayón Jiménez-Ugarte, Ignacio
  • Albizu-Arias, Xabier
  • Ríos-Insúa, David
  • Ibáñez, Juan José
  • Pérez-Pérez, Alejandro
  • Pizarroso, Jaime
  • Ruesca-Bonet, Berta
  • Rodríguez-Santana, Simón
  • Martínez, Laura M
Reconstructing the dietary ecology of fossil primates is essential for understanding how Pliocene–Pleistocene climatic reorganization shaped African ecosystems. During this interval, increasing aridity and climatic variability transformed habitats across eastern Africa, promoting ecological diversification among mammalian lineages. Papionins were key components of these faunas, yet their ecological differentiation remains incompletely resolved. Here, we investigate the dietary regimes of extinct papionins from the Turkana Basin using three-dimensional dental microwear texture analysis (DMTA) of buccal enamel surfaces combined with supervised machine-learning approaches. We analyzed buccal surface textures from fossil specimens of Parapapio ado, Parapapio lothagamensis, Theropithecus oswaldi, Cercopithecoides williamsi and Parapapio sp., applying ISO 25178, ISO 12781, Furrow, and SSFA parameters. After rigorous pre-processing and feature selection, Linear Discriminant Analysis and regularized multinomial logistic regression were used to assess taxonomic separability and identify key microtexture drivers. Cercopithecoides williamsi is characterized by highly distinctive buccal microtexture (notably deep furrows and elevated surface complexity), whereas Theropithecus oswaldi occupies the opposite end of the discriminant space, reflecting contrasting abrasive texture signatures. Parapapio lothagamensis forms a discrete cluster as the oldest taxon in the sample, clearly separated from Parapapio ado and other Parapapio, indicating early ecological divergence within the lineage. These findings demonstrate that buccal DMTA, integrated with machine-learning frameworks, provides a robust tool for resolving ecological differentiation in fossil primates and supports niche partitioning among Pliocene–Pleistocene papionins in the Turkana Basin during a period of major environmental change.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Machine learning approaches to dietary classification from dental microtexture in primates

  • Estebaranz-Sánchez, Ferran
  • Kit, Kristina
  • Ibáñez Estevez, Juan José
  • Insua, David R.
  • Rodríguez Santana, Simón
  • Martínez, Laura M.
Dental microwear texture (DMT) analysis is a critical proxy for reconstructing the diets of extant and extinct mammals. While craniodental morphology reflects selective pressures across evolutionary timescales, microwear captures localized, short-term dietary signals over weeks to months. However, the high dimensionality of modern 3D surface microtexture data, often spanning disparate parameter sets (such as ISO standards and scale-sensitive fractal analysis, SSFA), complicates classification, particularly when working with limited paleontological datasets. To address this, we present a robust machine learning pipeline designed to automatically classify primate samples () across 6 dietary groups and 7 species. Our methodology leverages a nested leave-one-out cross-validation framework to evaluate multiple classifiers, including multinomial logistic regression (MLR) with various regularization approaches, Naive Bayes, and tree-based ensemble algorithms (e.g., Random forests, XGBoost). Our results demonstrate that Lasso-regularized MLR and Naive Bayes yield the highest predictive performance while enforcing strict feature selection to maintain interpretability. Crucially, models relying exclusively on ISO parameters consistently outperformed those using SSFA, as ISO variables better capture the microroughness localized mechanical abrasions generated by specific diets in our dataset. Furthermore, the integration of novel Fourier-based descriptors and isotropy variables significantly enhanced models’ discriminating power. By providing a mathematically rigorous framework to isolate precise ecological signals from noisy, high-dimensional data, this approach enables more accurate and reproducible dietary classifications. Ultimately, refining these dietary reconstructions is essential for resolving broader questions regarding niche partitioning, species evolution, and paleoecological dynamics.